Mengram

What is Mengram?

Mengram is a persistent memory backend for AI agents that stores three types of memory—semantic (facts and preferences), episodic (events and decisions), and procedural (workflows that evolve from failures). It is designed for developers and teams who want their AI agents to retain context, learn from past interactions, and automatically improve workflows across sessions.

How to use Mengram?

Install via pip install mengram-ai or npm install mengram-ai, then run mengram setup to create an account and install Claude Code hooks, or manually set the MENGRAM_API_KEY environment variable. Use the Python/JavaScript client (e.g., Mengram(api_key="om-...")) or the CLI to add, search, and manage memories.

Key features of Mengram

• Stores three memory types: semantic, episodic, and procedural.
• Procedures automatically evolve when failures are detected.
• Cognitive profile generates a system prompt from all memories.
• Multi-user isolation with a single API key.
• Imports existing data from ChatGPT, Obsidian, or markdown files.
• Integrates with Claude Code, MCP, LangChain, CrewAI, and OpenClaw.

Use cases of Mengram

• Give Claude Code zero-config memory across sessions with auto-save and recall.
• Build a DevOps agent that learns from deployment failures and improves workflows.
• Create a customer support agent that remembers returning users and past issues.
• Develop a personal assistant that maintains a cognitive profile and chat history.

FAQ from Mengram

What makes Mengram different from other AI memory tools?

Mengram stores three memory types (semantic, episodic, procedural) and procedures evolve when they fail. It also offers a cognitive profile, Claude Code hooks, multi‑user isolation, and the ability to import from ChatGPT/Obsidian — features not commonly found in alternatives like Mem0, Zep, or Letta.

What are the runtime and dependency requirements?

Mengram requires Python 3.8+ (or Node.js for the JavaScript client) and an API key. The Python package depends on httpx; the async client requires pip install mengram-ai[async]. It runs as a cloud service — no local database needed.

Where does my data live?

Memories are stored on Mengram’s cloud service (accessed via https://mengram.io/v1/...). You can use the --cloud flag with CLI commands; the free tier is available at mengram.io. No local storage is used unless you self‑host (not mentioned as supported).

What transports and authentication does Mengram use?

Mengram uses HTTPS REST API calls with Bearer token authentication (the API key passed as api_key or via the MENGRAM_API_KEY environment variable). The MCP server runs over stdio transport. Webhooks can be set up to receive notifications on memory changes.

What is the pricing model?

Mengram offers a free tier. Paid plans start at $19–$249 per month for alternatives, but Mengram’s own pricing is not detailed beyond "Free tier" in the comparison table. A free API key can be obtained at mengram.io.